© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102246
    Prev
    Next
    INDEX
    Explanations

    contains 1

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on the numeric digit “1” (i.e. whenever the token “1” appears in the text).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彼の
    -2.02
    硖
    -1.94
    da
    -1.94
    genodigd
    -1.92
    شون
    -1.86
     ร์
    -1.85
     Lietu
    -1.83
    以上です
    -1.82
     nativo
    -1.78
     presentar
    -1.75
    POSITIVE LOGITS
    ↵
    2.66
     talvez
    2.33
     THE
    2.25
     provavelmente
    2.16
    the
    2.06
    that
    1.98
     THAT
    1.96
    とその
    1.84
     accordance
    1.84
    <i>
    1.84
    Activations Density 0.017%

    No Known Activations